Sequence modeling for predicting three-dimensional plasma etching profiles with deep learning
- 13 June 2025
- journal article
- Published by American Vacuum Society in Journal of Vacuum Science & Technology A
- Vol. 43 (4)
Abstract
Three-dimensional plasma etching profile evolution remains a fundamental challenge in semiconductor process engineering, especially given its complexity and computational cost. In this work, we present a data-driven sequence modeling framework for efficient and accurate prediction of three-dimensional plasma etch profiles. A physically calibrated simulation model was used to generate a comprehensive dataset, encompassing over 2000 time-resolved vertical (y–z) profile sequences and 1000 depth-resolved lateral (x–y) pattern clips, covering a wide range of process conditions and layout geometries representative of modern optical proximity correction patterns. Building on this dataset, we develop a Conditional Convolutional Recurrent Neural Network designed to predict the temporal and spatial evolution of etching contours. The model achieves robust predictive accuracy, with an average Structural Similarity Index Measure above 0.94 across predicted frames, and demonstrates consistent performance for both simple and complex feature arrangements. The sequence modeling approach allows for rapid generation of full etch profile sequences, reducing computation time by orders of magnitude compared to traditional simulation workflows. This framework provides an efficient solution for data-driven plasma etch profile prediction, supporting potential applications in process monitoring, virtual metrology, and layout-level risk assessment.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFF0605800)
- Key Research and Development Program of Zhejiang Province (2023C01017, 2022C01063, 2024C01002, 2024SJCZX0029)
This publication has 27 references indexed in Scilit:
- Optimizing Plasma Etching: Integrating Precise Three-Dimensional Etching Simulation and Machine Learning for Multi-Objective OptimizationIEEE Access, 2024
- Explainable artificial intelligence-based evidential inferencing on process faults in plasma etchingJournal of Physics D: Applied Physics, 2024
- Prediction of Global Ionospheric Total Electron Content (TEC) Based on SAM‐ConvLSTM ModelSpace Weather, 2023
- Abnormal Chamber Detection in the Etching Process Using Time-Series Data Augmentation and Soft LabelingIEEE Sensors Journal, 2023
- TCAD augmented generative adversarial network for hot-spot detection and mask-layout optimization in a large area HARC etching processPhysics of Plasmas, 2022
- A Deep Convolutional Autoencoder-Based Approach for Anomaly Detection With Industrial, Non-Images, 2-Dimensional Data: A Semiconductor Manufacturing Case StudyIEEE Transactions on Automation Science and Engineering, 2022
- Hybrid modelling of low temperature plasmas for fundamental investigations and equipment designJournal of Physics D: Applied Physics, 2009
- Investigation of etching and deposition processes of Cl2/O2/Ar inductively coupled plasmas on silicon by means of plasma–surface simulations and experimentsJournal of Physics D: Applied Physics, 2009
- Time series modeling of reactive ion etching using neural networksIEEE Transactions on Semiconductor Manufacturing, 1995
- Time series analysis, forecasting and controlIEEE Transactions on Automatic Control, 1972